Jorgen Lundman

dtruss shows all calls that mds does, and none of them are special. We also get noisy when something calls something we do not have, or support, - so we...

The smallest set where we have to report as "hfs" is if process_name() == "mds" or "coreservicesd". Then it works. coreservicesd stack looks like: ``` kernel.development`vfs_statfs+0xb zfs`zfs_vfs_getattr+0x2cc kernel.development`getattrlist_internal+0x6a6 kernel.development`getattrlistat_internal+0x11f kernel.development`getattrlist+0x70...

That spindump is showing `zget` getting stuck, waiting a tiny bit, and trying again.

Been trying to replicate this problem this morning, creating ~300,000 files and dirs to repeatedly, recursively, chown - but I am unable to make it misbehave. With and without xattrs,...

So you can reproduce it quite easily? Does it happen if you create a filesystem of empty files as well? For example: ``` find . \( -type d -exec mkdir...

https://github.com/openzfsonosx/zfs/issues/700

As a side comment, just wanted to mention it, the set_validdatalength() function: https://github.com/maharmstone/btrfs/blob/master/src/fileinfo.c#L3754 The "

Sounds like it tried to free a `buf` too many times, and the count of bugs went zero. It is also curious you are in `buf_strategy_vnode()` so you have picked...

@behlendorf Worth pointing out the PR did fix the leak problem, but does not fix the title of the ticket. `panic: VERIFY3(rc->rc_count == number) failed ` can still be triggered...

For me, I can trigger the assert `panic: VERIFY3(rc->rc_count == number) failed` more easily if I set `failmode=continue` and lower timeout. But it can be triggered with default ZFS timeout...